{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GIF5PX5NGZGTWDLVPL7TZ3JVFI","short_pith_number":"pith:GIF5PX5N","schema_version":"1.0","canonical_sha256":"320bd7dfad364d3b0d757aff3ced352a01e008c788baa033013ca86fd9a41248","source":{"kind":"arxiv","id":"2506.12218","version":2},"attestation_state":"computed","paper":{"title":"Directed Acyclic Graph Convolutional Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.SP","authors_text":"Gonzalo Mateos, Hamed Ajorlou, Samuel Rey","submitted_at":"2025-06-13T20:40:50Z","abstract_excerpt":"Directed acyclic graphs (DAGs) are central to science and engineering applications including causal inference, scheduling, and neural architecture search. In this work, we introduce the DAG Convolutional Network (DCN), a novel graph neural network (GNN) architecture designed specifically for convolutional learning from signals supported on DAGs. The DCN leverages causal graph filters to learn nodal representations that account for the partial ordering inherent to DAGs, a strong inductive bias does not present in conventional GNNs. Unlike prior art in machine learning over DAGs, DCN builds on f"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.12218","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SP","submitted_at":"2025-06-13T20:40:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"045260a3df1490ecda8d259106aa12f41f681f9737deb329e80a5ee71df516cc","abstract_canon_sha256":"015ebbac141d57327777f06f2b0402152c37a5f489b349efdaaea96665e8badc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T02:05:33.850581Z","signature_b64":"6VIpHR3FzyV9pAO89OOj3mLxP12bwwqkkCXoG+s6XPkm+6Hy77A4H/fwKNlbzZTUtg5C+TAxSoynTmpbukD7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"320bd7dfad364d3b0d757aff3ced352a01e008c788baa033013ca86fd9a41248","last_reissued_at":"2026-05-20T02:05:33.849804Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T02:05:33.849804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Directed Acyclic Graph Convolutional Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.SP","authors_text":"Gonzalo Mateos, Hamed Ajorlou, Samuel Rey","submitted_at":"2025-06-13T20:40:50Z","abstract_excerpt":"Directed acyclic graphs (DAGs) are central to science and engineering applications including causal inference, scheduling, and neural architecture search. In this work, we introduce the DAG Convolutional Network (DCN), a novel graph neural network (GNN) architecture designed specifically for convolutional learning from signals supported on DAGs. The DCN leverages causal graph filters to learn nodal representations that account for the partial ordering inherent to DAGs, a strong inductive bias does not present in conventional GNNs. Unlike prior art in machine learning over DAGs, DCN builds on f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12218","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.12218/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.12218","created_at":"2026-05-20T02:05:33.849927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12218v2","created_at":"2026-05-20T02:05:33.849927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12218","created_at":"2026-05-20T02:05:33.849927+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIF5PX5NGZGT","created_at":"2026-05-20T02:05:33.849927+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIF5PX5NGZGTWDLV","created_at":"2026-05-20T02:05:33.849927+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIF5PX5N","created_at":"2026-05-20T02:05:33.849927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GIF5PX5NGZGTWDLVPL7TZ3JVFI","json":"https://pith.science/pith/GIF5PX5NGZGTWDLVPL7TZ3JVFI.json","graph_json":"https://pith.science/api/pith-number/GIF5PX5NGZGTWDLVPL7TZ3JVFI/graph.json","events_json":"https://pith.science/api/pith-number/GIF5PX5NGZGTWDLVPL7TZ3JVFI/events.json","paper":"https://pith.science/paper/GIF5PX5N"},"agent_actions":{"view_html":"https://pith.science/pith/GIF5PX5NGZGTWDLVPL7TZ3JVFI","download_json":"https://pith.science/pith/GIF5PX5NGZGTWDLVPL7TZ3JVFI.json","view_paper":"https://pith.science/paper/GIF5PX5N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12218&json=true","fetch_graph":"https://pith.science/api/pith-number/GIF5PX5NGZGTWDLVPL7TZ3JVFI/graph.json","fetch_events":"https://pith.science/api/pith-number/GIF5PX5NGZGTWDLVPL7TZ3JVFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIF5PX5NGZGTWDLVPL7TZ3JVFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIF5PX5NGZGTWDLVPL7TZ3JVFI/action/storage_attestation","attest_author":"https://pith.science/pith/GIF5PX5NGZGTWDLVPL7TZ3JVFI/action/author_attestation","sign_citation":"https://pith.science/pith/GIF5PX5NGZGTWDLVPL7TZ3JVFI/action/citation_signature","submit_replication":"https://pith.science/pith/GIF5PX5NGZGTWDLVPL7TZ3JVFI/action/replication_record"}},"created_at":"2026-05-20T02:05:33.849927+00:00","updated_at":"2026-05-20T02:05:33.849927+00:00"}